# GPT-4o vs Grok 4.20 (Non-Reasoning)

> Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 28.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4o-vs-grok-4-20
- Last updated: 2026-10-10
- Shared benchmarks: 31

## Summary

- They share 31 benchmarks with published results for both. GPT-4o scores higher in 1 category and Grok 4.20 (Non-Reasoning) in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.2 to 9.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.4% for GPT-4o and 92.2% for Grok 4.20 (Non-Reasoning).
- Grok 4.20 (Non-Reasoning) is cheaper at $1.25 / $2.50 per million input/output tokens, against $2.50 / $10 for GPT-4o.
- Grok 4.20 (Non-Reasoning) accepts more context: 1M tokens versus 128K.

## Snapshot

| | GPT-4o | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 28.5 | 48.5 |
| Rank | 316 | 48 |
| Context | 128K | 1M |
| Input $/M | $2.50 | $1.25 |
| Output $/M | $10 | $2.50 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-4o: 25.1 (#323)
- Grok 4.20 (Non-Reasoning): 41.8 (#104)

| Benchmark | GPT-4o | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| WeirdML | 25.1% | 52.3% |
| LMArena Coding | 1297 | 1458 |
| SWE-bench Verified | 31% | — |
| SWE-bench Verified (bash only) | 21.6% | — |
| Aider Polyglot | 45.3% | — |
| LMArena WebDev | — | 1374 |
| GSO | 0% | — |
| BigCodeBench Instruct | 51.1% | — |
| LiveBench Coding | 51.4% | — |
| BigCodeBench Complete | 61.1% | — |
| CadEval | 26% | — |
| ALE-Bench | — | 1,150 |
| HumanEval+ | 87.2% | — |
| MBPP+ | 72.2% | — |

## Agentic & Tool Use

- GPT-4o: 20.8 (#133)
- Grok 4.20 (Non-Reasoning): 34.3 (#43)

| Benchmark | GPT-4o | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Search | 1006 | 1189 |
| Terminal-Bench | — | 57.3% |
| GDPval | 9.9% | — |
| TheAgentCompany | 8.6% | — |
| τ²-bench Banking | — | 18% |
| Cybench | 12.5% | — |
| BALROG | 32.3% | — |
| METR Time Horizons | 40.8% | — |
| Vending-Bench 2 | — | 4,663 |

## Reasoning

- GPT-4o: 9.4 (#338)
- Grok 4.20 (Non-Reasoning): 52.2 (#30)

| Benchmark | GPT-4o | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| ARC-AGI-2 | 0% | 65.1% |
| ARC-AGI-1 | 4.5% | 89.5% |
| Chess Puzzles | 13% | 24% |
| LMArena Hard Prompts | 1281 | 1451 |
| DTBench | 64.5% | 90.1% |
| LMCA | 16.6% | 38.7% |
| Epoch Capabilities Index | 128.97 | 152.01 |
| ForecastBench | 57.7 | 61.4 |
| SimpleBench | 17.8% | — |
| Kagi LLM Benchmark | — | 75% |
| NYT Connections (extended) | — | 85.4% |
| CritPt | 0% | — |
| EnigmaEval | 0.8% | — |
| Thematic Generalization | — | 63.8% |
| LiveBench Reasoning | 55.8% | — |
| LiveBench Data Analysis | 60.9% | — |
| LiveBench | 55.3% | — |

## Math

- GPT-4o: 10.2 (#303)
- Grok 4.20 (Non-Reasoning): 48.0 (#54)

| Benchmark | GPT-4o | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| FrontierMath (Tiers 1-3) | 0.4% | 44.9% |
| OTIS Mock AIME 2024-2025 | 6.4% | 92.2% |
| LMArena Math | 1285 | 1455 |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 14% |
| Omni-MATH | 29.3% | — |
| LiveBench Math | 49.5% | — |
| MATH Level 5 | 53.3% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |

## Knowledge

- GPT-4o: 28.8 (#235)
- Grok 4.20 (Non-Reasoning): 52.8 (#54)

| Benchmark | GPT-4o | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| GPQA Diamond | 49.2% | 89.3% |
| SimpleQA Verified | 26% | 30.2% |
| LMArena Expert | 1250 | 1440 |
| Humanity's Last Exam | 2.7% | — |
| MMLU-Pro | 71.3% | — |
| Confabulations | 15.3% | — |
| Vectara Hallucination Rate | 9.6% | — |
| GPQA (HELM) | 52% | — |
| MMLU | 88.1% | — |

## Multimodal

- GPT-4o: 33.9 (#85)
- Grok 4.20 (Non-Reasoning): 33.2 (#88)

| Benchmark | GPT-4o | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Vision | 1137 | 1263 |
| Video-MME | 71.9% | — |
| GeoBench | 71% | — |
| VPCT | 40% | — |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1416 |
| ScienceQA | 88.5% | — |

## Multilingual

- GPT-4o: 43.4 (#181)
- Grok 4.20 (Non-Reasoning): 54.7 (#38)

| Benchmark | GPT-4o | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Non-English | 1283 | 1440 |
| LMArena Chinese | 1277 | 1481 |
| LMArena French | 1303 | 1477 |
| LMArena German | 1282 | 1463 |
| LMArena Japanese | 1257 | 1450 |
| LMArena Korean | 1234 | 1417 |
| LMArena Russian | 1286 | 1457 |
| LMArena Spanish | 1292 | 1442 |

## Instruction Following

- GPT-4o: 66.8 (#202)
- Grok 4.20 (Non-Reasoning): 75.0 (#79)

| Benchmark | GPT-4o | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Instruction Following | 1278 | 1420 |
| LiveBench Instruction Following | 68.6% | — |
| IFEval | 81.7% | — |

## Long Context

- GPT-4o: 39.4 (#174)
- Grok 4.20 (Non-Reasoning): 45.4 (#33)

| Benchmark | GPT-4o | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Longer Query | 1289 | 1436 |
| Fiction.LiveBench | 66.7% | — |
| CL-bench | — | 22.2% |
| CL-bench Life | — | 11.9% |

## Writing & Preference

- GPT-4o: 52.8 (#160)
- Grok 4.20 (Non-Reasoning): 65.9 (#42)

| Benchmark | GPT-4o | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Text | 1300 | 1451 |
| LMArena Creative Writing | 1291 | 1439 |
| LMArena Multi-Turn | 1302 | 1456 |
| Short-Story Creative Writing | 81.8% | — |
| EQ-Bench Creative Writing | — | 1574 |
| WildBench | 82.8% | — |
| LiveBench Language | 47.6% | — |

## FAQ

### Is GPT-4o better than Grok 4.20 (Non-Reasoning)?

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 28.5 on the Noometry Index.

### Which is cheaper, GPT-4o or Grok 4.20 (Non-Reasoning)?

Grok 4.20 (Non-Reasoning) is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; GPT-4o lists at $2.50 and $10.

### Is GPT-4o or Grok 4.20 (Non-Reasoning) better for coding?

Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 41.8 versus 25.1 in the Noometry coding category.

### Which has the bigger context window?

Grok 4.20 (Non-Reasoning) does, with 1M tokens against 128K.

### How many benchmarks do GPT-4o and Grok 4.20 (Non-Reasoning) share?

31 benchmarks have published results for both models. GPT-4o has 72 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.